Deion of the bug: Currently, this code: <div class="high

I'm not sure it needs anything other than: <a class="issue-link js-issue-link" data-er

`count_tokens` should allow empty content about generative-ai-python HOT 2 CLOSED

markmcd commented on June 12, 2024

`count_tokens` should allow empty content

from generative-ai-python.

Comments (2)

mayureshagashe2105 commented on June 12, 2024

yeah...protos mark contents as optional when passed individually, but is a required field when passing with the entire GenerateContentRequest. Current implementation converts passed params to GenerateContentRequest regardless.

A possible fix could be( on line 338 ):

if not contents:
    contents = [""]

generative-ai-python/google/generativeai/generative_models.py

Lines 323 to 340 in bb58ab8

 def count_tokens( 

 self, 

 contents: content_types.ContentsType = None, 

 *, 

 generation_config: generation_types.GenerationConfigType | None = None, 

 safety_settings: safety_types.SafetySettingOptions | None = None, 

 tools: content_types.FunctionLibraryType | None = None, 

 tool_config: content_types.ToolConfigType | None = None, 

 request_options: dict[str, Any] | None = None, 

 ) -> glm.CountTokensResponse: 

 if request_options is None: 

 request_options = {} 

 if self._client is None: 

 self._client = client.get_default_generative_client() 

 request = glm.CountTokensRequest( 

 model=self.model_name,

Not sure, if this is a good fix. (will it increase the token count, as a blank token is also being passed to the req?)

from generative-ai-python.

MarkDaoust commented on June 12, 2024

I'm not sure it needs anything other than: #342

from generative-ai-python.

`count_tokens` should allow empty content about generative-ai-python HOT 2 CLOSED

Comments (2)

Related Issues (20)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent

	def count_tokens(
	self,
	contents: content_types.ContentsType = None,
	*,
	generation_config: generation_types.GenerationConfigType \| None = None,
	safety_settings: safety_types.SafetySettingOptions \| None = None,
	tools: content_types.FunctionLibraryType \| None = None,
	tool_config: content_types.ToolConfigType \| None = None,
	request_options: dict[str, Any] \| None = None,
	) -> glm.CountTokensResponse:
	if request_options is None:
	request_options = {}

	if self._client is None:
	self._client = client.get_default_generative_client()

	request = glm.CountTokensRequest(
	model=self.model_name,